© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16236
    Prev
    Next
    INDEX
    Explanations

    opinion of the court

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     perfectly
    -0.12
     apro
    -0.11
    /dom
    -0.11
     effortlessly
    -0.11
    unda
    -0.11
    ghi
    -0.10
     calmly
    -0.10
     unab
    -0.10
    -ready
    -0.10
     smoothly
    -0.10
    POSITIVE LOGITS
     joke
    0.08
    ipse
    0.08
    addock
    0.08
     fif
    0.07
    ceb
    0.07
    /logout
    0.07
    desired
    0.07
     Mobil
    0.07
     \<
    0.07
     Kimberly
    0.07
    Activations Density 0.003%

    No Known Activations